skills/deepseek-ai/deepseek-harness/dsh-pr-description/Snyk

dsh-pr-description

Warn

Audited by Snyk on Oct 25, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read existing PR descriptions or issues via gh CLI tools (e.g. gh pr view), which ingest outsider-authored free text from pull request comments and descriptions.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 25, 2026, 08:02 PM

Issues

1